The densenet-121
model is one of the DenseNet* group of models designed to perform image classification. The authors originally trained the models on Torch*, but then converted them into Caffe* format. All DenseNet models have been pretrained on the ImageNet image database. For details about this family of models, check out the repository.
Metric | Value |
---|---|
Type | Classification |
GFLOPs | 5.724 |
MParams | 7.971 |
Source framework | Caffe* |
Metric | Value |
---|---|
Top 1 | 74.42% |
Top 5 | 92.136% |
The model input is a blob that consists of a single image of 1x3x224x224 in BGR order. Before passing the image blob into the network, subtract BGR mean values as follows: [103.94, 116.78, 123.68]. In addition, values must be divided by 0.017.
Image, name - data
, shape - 1,3,224,224
, format is B,C,H,W
where:
B
- batch sizeC
- channelH
- heightW
- widthChannel order is BGR
. Mean values - [103.94,116.78,123.68], scale value - 58.8235294117647
Image, name - data
, shape - 1,3,224,224
, format is B,C,H,W
where:
B
- batch sizeC
- channelH
- heightW
- widthChannel order is BGR
.
The model output for densenet-121
is a typical object classifier output for 1000 different classifications matching those in the ImageNet database.
Object classifier according to ImageNet classes, name - fc6
, shape - 1,1000,1,1
, contains predicted probability for each class in logits format.
Object classifier according to ImageNet classes, name - fc6
, shape - 1,1000,1,1
, contains predicted probability for each class in logits format.
You can download models and if necessary convert them into Inference Engine format using the Model Downloader and other automation tools as shown in the examples below.
An example of using the Model Downloader:
An example of using the Model Converter:
The original model is distributed under the following license: